Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 48691
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    心理
    -0.10
     romant
    -0.10
    Diary
    -0.09
    Markdown
    -0.09
    Instagram
    -0.09
     ruin
    -0.09
     interpersonal
    -0.09
     acquaintances
    -0.09
    办理
    -0.09
    婚
    -0.09
    POSITIVE LOGITS
     GPUs
    0.19
     FPGA
    0.17
     Intel
    0.17
     CPUs
    0.17
     motherboard
    0.16
     Nvidia
    0.15
     silicon
    0.15
     GPU
    0.15
     Cpu
    0.15
     CPU
    0.15
    Activations Density 0.045%

    No Known Activations